Pereiti prie pagrindinio turinio
OpenAI

2025 m. balandžio 16 d.

LeidimasProduktas

Introducing OpenAI o3 and o4-mini

Įkeliama...

2025 m. birželio 10 d. atnaujinimas: „OpenAI o3‑pro“ dabar prieinama „Pro“ naudotojams „ChatGPT“ platformoje, taip pat mūsų API. Kaip ir „OpenAI o1‑pro“, „o3‑pro“ yra mūsų išmaniausio modelio „OpenAI o3“ versija, sukurta galvoti ilgiau ir pateikti patikimiausius atsakymus. Visą informaciją rasite mūsų laidos pastabose(atsidaro naujame lange).


Šiandien pristatome „OpenAI o3“ ir „o4-mini“ – naujausius mūsų „o“ serijos modelius, išmokytus galvoti ilgiau prieš atsakant. Tai išmaniausi modeliai, kokius esame išleidę iki šiol, žymintys kokybinį „ChatGPT“ galimybių pokytį visiems – nuo smalsių naudotojų iki pažengusių tyrėjų. Pirmą kartą mūsų samprotavimo modeliai gali agentiškai naudoti ir derinti visus įrankius – paiešką internete, įkeltų failų ir kitų duomenų analizę naudojant „Python“, gilų vizualinių įvesčių samprotavimą ir net vaizdų generavimą – „ChatGPT“ aplinkoje. Svarbu tai, kad šie modeliai išmokyti samprotauti, kada ir kaip naudoti įrankius, kad greitai (paprastai greičiau nei per minutę) pateiktų išsamius ir apgalvotus atsakymus tinkamais išvesties formatais sudėtingesnėms problemoms spręsti. Tai leidžia jiems efektyviau spręsti įvairialypius klausimus – tai žingsnis link savarankiškesnio „ChatGPT“, galinčio vykdyti užduotis jūsų vardu. Derinant pažangiausius samprotavimo gebėjimus su visiška prieiga prie įrankių, gaunamas gerokai stipresnis našumas akademiniuose lyginamuosiuose standartuose ir realiojo pasaulio užduotyse, nustatant naują intelekto ir naudingumo standartą.

Kas pasikeitė

OpenAI o3 yra mūsų galingiausias samprotavimo modelis, plečiantis ribas programavimo, matematikos, mokslo, vizualinio suvokimo ir kitose srityse. Jis nustato naują pažangiausių technologijų (SOTA) standartą tokiuose lyginamuosiuose standartuose kaip „Codeforces“, „SWE-bench“ (nekuriant pasirinktinio modeliui skirto karkaso) ir MMMU. Jis idealiai tinka sudėtingoms užklausoms, reikalaujančioms visapusės analizės, ir kurių atsakymai nebūtinai iš karto yra akivaizdūs. Jis ypač gerai atlieka vizualines užduotis, pavyzdžiui, analizuoja vaizdus, diagramas ir grafikus. Išorės ekspertų vertinimais, atlikdamas sudėtingas realiojo pasaulio užduotis, „o3“ padaro 20 proc. mažiau didelių klaidų nei „OpenAI o1“, ypač tokiose srityse kaip programavimas, verslas / konsultavimas ir kūrybinių idėjų generavimas. Ankstyvieji testuotojai pabrėžė jo analitinį tikslumą veikiant kaip mąstymo partneriui ir akcentavo gebėjimą generuoti bei kritiškai vertinti naujas hipotezes – ypač biologijos, matematikos ir inžinerijos kontekstuose.

„OpenAI“ o4-mini yra mažesnis modelis, optimizuotas greitam, ekonomiškam samprotavimui; jis pasiekia puikų našumą, atsižvelgiant į jo dydį ir kainą, ypač matematikos, programavimo ir vizualinėse užduotyse. Tai geriausiai veikiantis lyginamasis modelis AIME 2024 ir 2025 konkursuose. Nors prieiga prie kompiuterio reikšmingai sumažina AIME egzamino sunkumą, taip pat pastebėjome, kad „o4-mini“ pasiekia 99,5 proc. „pass@1“ (100 proc. „consensus@8“) AIME 2025 konkurse, kai suteikiama prieiga prie „Python“ interpretatoriaus. Nors šių rezultatų nereikėtų lyginti su modelių, neturinčių prieigos prie įrankių, našumu, jie yra vienas iš pavyzdžių, kaip efektyviai „o4-mini“ išnaudoja turimus įrankius; „o3“ dėl įrankių naudojimo AIME 2025 konkurse rodo panašius pagerėjimus (98,4 proc. „pass@1“, 100 proc. „consensus@8“).

Ekspertų vertinimais, „o4-mini“ taip pat lenkia savo pirmtaką „o3‑mini“ ne STEM užduotyse, taip pat tokiose srityse kaip duomenų mokslas. Dėl savo efektyvumo „o4-mini“ palaiko žymiai didesnius naudojimo limitus nei „o3“, todėl tai yra stiprus didelės apimties ir didelio pralaidumo pasirinkimas klausimams, kuriems naudingas samprotavimas. Išoriniai ekspertai vertintojai nurodė, kad abu modeliai demonstruoja geresnį instrukcijų laikymąsi ir pateikia naudingesnius, patikrinamus atsakymus nei jų pirmtakai, nes pasižymi didesniu intelektu ir įtraukia interneto šaltinius. Palyginti su ankstesnėmis mūsų samprotavimo modelių iteracijomis, šie du modeliai taip pat turėtų atrodyti natūralesni ir labiau priminti pokalbį, ypač todėl, kad jie remiasi atmintimi ir ankstesniais pokalbiais, kad atsakymai būtų labiau individualizuoti ir aktualūs.

Multimodalinis

Programavimas

Visiems „SWE-bench“ vertinimams naudojamas fiksuotas n=477 patikrintų užduočių poaibis, patvirtintas mūsų vidaus infrastruktūroje.

Instrukcijų laikymasis ir įrankių naudojimas agento režimu

Visi modeliai vertinami taikant didelių „samprotavimo pastangų“ (angl. reasoning effort) nuostatas – panašiai kaip variantuose „o4-mini-high“ „ChatGPT“ aplinkoje.

Continuing to scale reinforcement learning

Throughout the development of OpenAI o3, we’ve observed that large-scale reinforcement learning exhibits the same “more compute = better performance” trend observed in GPT‑series pretraining. By retracing the scaling path—this time in RL—we’ve pushed an additional order of magnitude in both training compute and inference-time reasoning, yet still see clear performance gains, validating that the models’ performance continues to improve the more they’re allowed to think. At equal latency and cost with OpenAI o1, o3 delivers higher performance in ChatGPT—and we've validated that if we let it think longer, its performance keeps climbing.

We also trained both models to use tools through reinforcement learning—teaching them not just how to use tools, but to reason about when to use them. Their ability to deploy tools based on desired outcomes makes them more capable in open-ended situations—particularly those involving visual reasoning and multi-step workflows. This improvement is reflected both in academic benchmarks and real-world tasks, as reported by early testers.

Mąstymas remiantis vaizdais

ChatGPT thinking with images

Pirmą kartą šie modeliai gali integruoti vaizdus tiesiogiai į savo minčių grandinę. Jie ne tik mato vaizdą – jie mąsto remdamiesi juo. Tai atveria naują problemų sprendimo klasę, kurioje derinamas vizualinis ir tekstinis samprotavimas, atsispindintis jų pažangiausiuose rezultatuose multimodaliniuose lyginamuosiuose standartuose.

Žmonės gali įkelti baltosios lentos nuotrauką, vadovėlio diagramą ar ranka pieštą eskizą, ir modelis gali jį interpretuoti – net jei vaizdas yra neryškus, apverstas ar prastos kokybės. Naudodami įrankius, modeliai gali manipuliuoti vaizdais – pasukti, priartinti ar transformuoti juos samprotaudami.

Šie modeliai pasižymi geriausiu klasėje tikslumu atliekant vizualinio suvokimo užduotis, todėl gali išspręsti klausimus, kurie anksčiau buvo neįveikiami. Peržiūrėkite vizualinio samprotavimo tyrimų tinklaraščio įrašą, kad sužinotumėte daugiau.

„OpenAI o3“ ir „o4-mini“ turi visišką prieigą prie įrankių „ChatGPT“ aplinkoje, taip pat prie jūsų pasirinktinių įrankių per funkcijų iškvietimą API sąsajoje. Šie modeliai išmokyti samprotauti, kaip spręsti problemas, pasirenkant, kada ir kaip naudoti įrankius, kad greitai – paprastai greičiau nei per minutę – pateiktų išsamius ir apgalvotus atsakymus tinkamais išvesties formatais.

Pavyzdžiui, naudotojas gali paklausti: „Kaip, palyginti su praėjusiais metais, atrodys energijos sąnaudos vasarą Kalifornijoje?“. Modelis gali ieškoti viešųjų komunalinių paslaugų duomenų internete, parašyti „Python“ kodą prognozei sudaryti, sugeneruoti grafiką ar vaizdą ir paaiškinti pagrindinius veiksnius, lėmusius prognozę, sujungdamas kelis įrankių iškvietimus į grandinę. Samprotavimo funkcija padeda modeliams reaguoti ir prireikus keisti kryptį atsižvelgiant į aptiktą informaciją. Pavyzdžiui, jie gali kelis kartus ieškoti internete naudodamiesi paieškos teikėjų pagalba, peržiūrėti rezultatus ir bandyti naujas paieškas, jei reikia daugiau informacijos.

Šis lankstus, strateginis požiūris leidžia modeliams atlikti užduotis, reikalaujančias prieigos prie naujausios informacijos, kuri nėra įtraukta į modelio vidaus žinias, išplėsto samprotavimo, sintezės ir išvesties generavimo įvairiais modalumais funkcijas.

Visi pavyzdžiai gauti naudojant „OpenAI o3“.

OpenAI o3

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

55 sekundes samprotauta apie polinomo sudarymą
  • The curve defined by p(x) = p(y) factors if p(x) is decomposable or has repeated factors. Actually, p(x)-p(y) always factors, and it’s divisible by (x-y). This gives one factor, and the rest is a degree d-1 polynomial in x and y. For the curve to have at least three irreducible components, p(x)-p(y) must factor into at least three nontrivial factors. Each factor corresponds to a component in projective space, and at least one must be nonlinear.
  • I’m checking the Dickson polynomials D_n(x,a) and focusing on their coefficients. With a=1, it seems the leading coefficient is always 1, confirming that Dickson polynomials are monic. The linear coefficient for odd n is following a predictable sign pattern: for n=19, it gives a coefficient of -19, which is exactly what I need. So the Dickson polynomial D_n(x,1) with odd n fits nicely with the linear coefficient I was looking for.
  • I've confirmed that the linear coefficient for p(x)=D19(x)p(x) = D_{19}(x)p(x)=D19​(x) is correct, with the necessary scaling factor to match. Now for the next step, I need to compute D19(19)D_{19}(19)D19​(19). Since Tn(z)T_n(z)Tn​(z) grows quickly for real z>1z > 1z>1, I plan to compute this value using Python, leveraging the recurrence to avoid mistakes—it's going to be a big number. I'll make sure to present the numeric result neatly so it's understandable since the coefficients are integers.
  • The Dickson polynomial D_{19}(x,1) is confirmed to have the required properties: monic, odd, real coefficients, and a linear coefficient of -19. The factorization of D_{19}(x) into irreducible components is also verified and satisfies the condition of having at least 10 components (1 linear + 9 quadratics). To compute p(19), we'll use the recurrence relation for Dickson polynomials, but there's also a closed-form expression involving cosine that could be handy here. I'll proceed accordingly!
  • I confirmed the linear coefficient is working correctly, which means now I need to calculate p(19)=D19(19)p(19) = D_{19}(19)p(19)=D19​(19). This involves evaluating T19(9.5)T_{19}(9.5)T19​(9.5), which grows rapidly. To ensure I get an accurate result, I'll compute this using recurrence in Python. The result is a large number: 1,876,572,071,974,094,803,391,179. I'll use the commas to make it easier to read: p(19)=1,876,572,071,974,094,803,391,179p(19) = 1,876,572,071,974,094,803,391,179p(19)=1,876,572,071,974,094,803,391,179.
  • For a = 1, there’s a relationship between Dickson polynomials and Chebyshev polynomials: D_n(x, 1) = 2^(n-1) T_n(x/2). Checking this, we see that the definition of D_n(u + 1/u) aligns well with Chebyshev’s formula. By setting x = 2 cos(θ), we find that D_n(x) equals 2 T_n(x/2). Importantly, the leading coefficient works out to 1, confirming the identity holds. This is nice!
  • Now, I need to verify that p(x)−p(y)p(x) - p(y)p(x)−p(y) factors as desired, relying on the known Dickson polynomial factorization. According to the literature (like Fried and Jarden), the difference Dn(x)−Dn(y)D_n(x) - D_n(y)Dn​(x)−Dn​(y) factors into a product involving (x−y)(x - y)(x−y) and other expressions. I'll provide the explicit polynomial D19(x,1)D_{19}(x, 1)D19​(x,1), list the coefficients, and explain how it satisfies the desired properties: monic, odd, etc. Lastly, I'll compute p(19)p(19)p(19).

Analyzed

Python

1
from math import comb, cos, acos
2
# Let's compute Dickson D_n(x,a=1) recursively
3
def dickson(n,x,a=1):
4
if n==0:
5
return 2
6
if n==1:
7
return x
8
Dm2=2
9
Dm1=x
10
for k in range(2,n+1):
11
D= x*Dm1 - a*Dm2
12
Dm2, Dm1 = Dm1, D
13
return Dm1
14

15
d19 = dickson(19,19,1)
16
d19

1876572071974094803391179

Analyzed

Python

1
d19

1876572071974094803391179

Analyzed

Python

1
import locale, sys, math, json, textwrap, re, decimal

Analyzed

Python

1
"{:,}".format(d19)

'1,876,572,071,974,094,803,391,179'

Analyzed

Python

1
# compute coefficients of Dickson polynomial D_n(x,1) via recurrence polynomial representation
2
from sympy import symbols, Poly
3

4
x = symbols('x')
5
def dickson_poly(n):

Poli(x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x, x,

Analyzed

Python

1
poly19.as_expr()

x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x

Done

A convenient way to force many factors in
p(x)    p(y)p(x) \;-\; p(y) is to use a Dickson polynomial of the first kind.
For a parameter
aCa \in \mathbb{C} in math these are defined by

D0 ⁣(x,a)=2,  D1 ⁣(x,a)=x,  Dn ⁣(x,a)=xDn1 ⁣(x,a)aDn2 ⁣(x,a)(n2),D_0\!\left(x,\, a\right) = 2,\; D_1\!\left(x,\, a\right) = x,\; D_n\!\left(x,\, a\right) = x\,D_{n-1}\!\left(x,\, a\right) - a\,D_{n-2}\!\left(x,\, a\right)\quad (n \ge 2),

and satisfy the functional identity

Dn ⁣(u+au,a)=un+anun.D_n\!\left(u + \frac{a}{u},\, a\right) = u^{n} + \frac{a^{n}}{u^{n}}.


1. Choosing the polynomial

Take a=1a = 1 and n=19n=19.
Because
nn is odd, D19 ⁣(x,1)D_{19}\!\left(x,\, 1\right) is an odd polynomial; the recurrence immediately shows it is monic and has integer (hence real) coefficients.
The coefficient of
xx is x=(1)n12n=19,x = (-1)^{\frac{n-1}{2}}\,n = -19, so all requested normalisations are satisfied.

Writing it out gives

p(x)=D19 ⁣(x,1)=x1919x17+152x15665x13+1729x112717x9+2508x71254x5+285x319x. \boxed{% p(x) = D_{19}\!\left(x,1\right) = x^{19} - 19x^{17} + 152x^{15} - 665x^{13} + 1729x^{11} - 2717x^{9} + 2508x^{7} - 1254x^{5} + 285x^{3} - 19x% }\,.


2. Irreducible components of fX  =  {p(x)=p(y)}fX \;=\; \bigl\{\, p(x) = p(y) \,\bigr\}

For Dickson polynomials one has the classical factorisation

Dn ⁣(x,1)    Dn ⁣(y,1)  =  (xy)j=1n12(x2+y22cos ⁣(2πjn)xy4sin2 ⁣(πjn)),D_n\!\left(x,1\right) \;-\; D_n\!\left(y,1\right) \;=\; (x - y)\, \prod_{j=1}^{\frac{n-1}{2}} \Bigl( x^{2} + y^{2} - 2\cos\!\bigl(\tfrac{2\pi j}{n}\bigr)\,xy - 4\sin^{2}\!\bigl(\tfrac{\pi j}{n}\bigr) \Bigr),

where each quadratic factor is irreducible over C\mathbb{C} (see, e.g., Lidl–Niederreiter, Finite Fields, §3.6).
For
n=19n=19 this gives

  • one linear component x=y;x=y;
  • nine quadratic components (corresponding to (j=1,,9).\bigl(j = 1,\,\ldots,\,9\bigr).

Hence XP1×P1X \subset \mathbb{P}^{1} \times \mathbb{P}^{1} has 1010 irreducible components, at least three of them and not all linear, as required.


3. Evaluating p(19)p(19)

Using the recurrence (or the identity Dn ⁣(x,1)  =  2Tn ⁣(x2)D_n\!\left(x,\,1\right) \;=\; 2\,T_n\!\bigl(\tfrac{x}{2}\bigr) with Chebyshev TnT_n one obtains

p(19)  =  D19 ⁣(19,1)  =  1876572071974094803391179.p(19) \;=\; D_{19}\!\left(19,\,1\right) \;=\; 1\,876\,572\,071\,974\,094\,803\,391\,179.


Thus the polynomial above fulfils every condition, and

p(19)  =  1,876,572,071,974,094,803,391,179.\boxed{% p(19) \;=\; 1{,}876{,}572{,}071{,}974{,}094{,}803{,}391{,}179 }.

OpenAI o1

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

Galvojo 1 min. 19 sek.

I’m piecing together a degree 19 polynomial with only odd powers and a linear coefficient of -19, like: p(x)=x19+a17x17+…+a1xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_1xp(x)=x19+a17​x17+…+a1​x.

I'm examining if the polynomial p(x)=x19+a17x17+…+a3x3−19xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_3x^3 - 19xp(x)=x19+a17​x17+…+a3​x3−19x has a notable classical form, considering symmetry or factorization for multiple irreducible components.

To ensure p(x)p(x)p(x) has three or more irreducible components, I’m considering the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) into at least three irreducible factors in C[x,y]\mathbb{C}[x,y]C[x,y].

I'm working through x19−y19x^{19} - y^{19}x19−y19 to ensure it balances linear and nonlinear factors, aiming for a polynomial with at least three irreducible components that aren't all linear.

Taking a closer look at how p(x)−p(y)p(x) - p(y)p(x)−p(y) can be factored into three distinct polynomials in xxx, aiming to achieve the desired irreducible components.

I'm thinking about how composing ppp with simpler polynomials, like xm−cx^m - cxm−c, could result in multiple irreducible components, achieving at least three distinct factors.

I’m exploring the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) with cyclotomic polynomials. This method generates nnn linear irreducible factors, which might not achieve the required three distinct components.

I'm focusing on constructing an "odd" and monic polynomial, ensuring all exponents are odd and the leading term is x19x^{19}x19. This approach aims to achieve the desired factorization.

I'm working with the Chebyshev polynomials to ensure p(x)−p(y)p(x) - p(y)p(x)−p(y) has at least three irreducible components, leveraging their even or odd properties to manage coefficients.

Considering the odd Chebyshev polynomial T19(x)T_{19}(x)T19​(x) for potential factorization, while also examining composite polynomials of lower degrees to enhance factorization properties.

I'm analyzing how a polynomial composed of lower-degree polynomials, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, could yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components.

Piecing together polynomials with integer coefficients, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, to achieve factorization in p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components, aiming for degree 19.

I’m examining how p(x)=(x3−3x)kp(x) = (x^3 - 3x)^kp(x)=(x3−3x)k or p(x)=x19−19xp(x) = x^19 - 19xp(x)=x19−19x might yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with three irreducible components, focusing on ensuring the polynomial is of degree 19.

I’m analyzing p(x)−p(y)p(x) - p(y)p(x)−p(y) into (x−y)(x18+x17y+…+y18−19)(x-y)(x^{18} + x^{17}y + \ldots + y^{18} - 19)(x−y)(x18+x17y+…+y18−19) to identify irreducible components. The polynomial factor x18+x17y+…+y18−19x^{18} + x^{17}y + \ldots + y^{18} - 19x18+x17y+…+y18−19 remains challenging to factor further.

I’m thinking through a new approach: adjusting the Chebyshev polynomial T19(x)T_{19}(x)T19​(x) to make it monic, aiming to achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

OK, let's think through. I’m tweaking T19(x)T_{19}(x)T19​(x)'s coefficients to keep the polynomial monic and check if it simplifies into multiple irreducible components.

I'm thinking over various factorization strategies for a monic polynomial of degree 19. The goal is to ensure at least one non-linear factor and achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

I’m updating my approach to factor x2+xy+y2−1x^2 + xy + y^2 - 1x2+xy+y2−1 over complex numbers by exploring change of variables and third roots of unity. This helps in achieving the desired polynomial structure.

I'm combining x3−xx^3 - xx3−x with x19−19xx^{19} - 19xx19−19x to tweak the polynomial's coefficients and complexity, aiming to include more non-linear factors for the desired irreducibility.

Piecing together p(x)=x19−x3−19xp(x) = x^{19} - x^3 - 19xp(x)=x19−x3−19x to ensure it’s odd, monic, and has the required linear coefficient. This targets the desired irreducible factorizations.

I’m mapping out the second factor x18+…+y18−x2−xy−y2−19x^{18} + \ldots + y^{18} - x^2 - xy - y^2 - 19x18+…+y18−x2−xy−y2−19 to see if it can split into three irreducible components.

I’m considering methods to factorize the polynomial by making it divisible by x−yx - yx−y and ensuring the remaining factor splits into exactly two irreducible components, aiming for a less complex factorization.

I’m examining the polynomial x18+x17y+…+y18x^{18} + x^{17}y + \ldots + y^{18}x18+x17y+…+y18 and noting it simplifies to x19−y19x−y\frac{x^{19} - y^{19}}{x - y}x−yx19−y19​, which might reveal further irreducible factors.

I’m mapping out the polynomial x(x18−1)−y(y18−1)x−y\frac{x(x^{18}-1) - y(y^{18}-1)}{x-y}x−yx(x18−1)−y(y18−1)​ for further factorization. This might yield just two irreducible components, which falls short of three.

I’m exploring whether the polynomial p(x)=x19−(x3)p(x) = x^19 - (x^3)p(x)=x19−(x3) can be expressed as the composition of a smaller polynomial with xkx^kxk, potentially revealing multiple irreducible components.

I'm examining if the polynomial T19(x)T_{19}(x)T19​(x) can be factored using trigonometric identities, seeking partial factorization without fully linearizing, to gain multiple irreducible components.

OK, let me see. Trigonometric identities show multiple solutions for θ\thetaθ and ϕ\phiϕ, likely leading to 19 or 38 linear factors for T19(x)T_{19}(x)T19​(x).

I’m examining how the equation arccos⁡x=±arccos⁡y+2kπ19\arccos x = \pm \arccos y + \frac{2k\pi}{19}arccosx=±arccosy+192kπ​ leads to possible multiple branches, potentially irreducible in the algebraic sense, and needing an example with at least three non-linear irreducible components.

OK, let me see. I’m pulling together details on the polynomial x3(x2−1)8+xx^3 (x^2 - 1)^8 + xx3(x2−1)8+x. It’s monic, with x19x^{19}x19 as the leading term, ensuring it meets key criteria.

I’m noting that the polynomial p(x)=x3(x2−1)8+xp(x) = x^3 (x^2 - 1)^8 + xp(x)=x3(x2−1)8+x is odd, with its linear coefficient patterning to -19.

I’m figuring out how to adjust the linear coefficient of polynomial p(x)p(x)p(x) to -19 by adding a constant factor ccc in front of xxx to ensure it’s adequately modified.

By tweaking the linear coefficient of p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to -19, it ensures the polynomial remains monic, odd, and real.

I’m working on adding a constant factor ccc to xxx in p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to ensure the linear coefficient is -19, making the polynomial monic, odd, and real.

I'm piecing together the polynomial p(x)=x3(x−1)8(x+1)8p(x) = x^3 (x-1)^8 (x+1)^8p(x)=x3(x−1)8(x+1)8 and considering how p(x)−p(y)p(x) - p(y)p(x)−p(y) might factor with factors like x−yx-yx−y.

I’m confirming p(x)p(x)p(x) is monic, odd, and real, with a linear coefficient of -19, by expanding x3(x2−1)8x^3 (x^2 -1)^8x3(x2−1)8 to set the constant ccc.

I found that for p(x) to have a coefficient of -19 for the x term, c must be -19. The polynomial, p(x), incorporates this constant and preserves the original polynomial's structure.

Below is one concrete example (over the reals) of an odd, monic, degree 19 polynomial with linear coefficient 19-19 whose zero-locus relation {p(x)=p(y)} in P1×P1\{\,p(x)=p(y)\,\}\ \text{in }\mathbb{P}^{1}\times\mathbb{P}^{1} splits into at least three irreducible components (and not all components are linear). We then compute p(19)p(19).


1. The polynomial

Consider

p(x)  =  x3(x21)8    19x.p(x) \;=\; x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;-\; 19x.

We can expand

x3(x21)8  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3.x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;=\; x^{19}\;-\;8x^{17}\;+\;28x^{15}\;-\;56x^{13}\;+\;70x^{11} \;-\;56x^{9}\;+\;28x^{7}\;-\;8x^{5}\;+\;x^{3}.

Hence

p(x)  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3    19x.p(x) \;=\; x^{19} \;-\; 8x^{17} \;+\; 28x^{15} \;-\; 56x^{13} \;+\; 70x^{11} \;-\; 56x^{9} \;+\; 28x^{7} \;-\; 8x^{5} \;+\; x^{3} \;-\; 19x.

Checking the required properties

Degree 19, monic:
The leading term is
x19x^{19}with coefficient 11.

Odd polynomial:
All exponents are odd
(19,17,,3,1),\bigl(19,\,17,\,\ldots,\,3,\,1\bigr), and the constant term is 00. Indeed,

p(x)  =  p(x),p(-x) \;=\; -\,p(x),

which makes pp an odd polynomial.

Real coefficients:
All coefficients are real integers.

Linear coefficient 19-19:
The coefficient of
xx is clearly 19-19.

At least three irreducible components, not all linear:
Over
C\mathbb{C}, the locus

X  =  {(x,y):p(x)=p(y)}    P1×P1X \;=\; \bigl\{\, (x,y) : p(x)=p(y) \,\bigr\} \;\subset\; \mathbb{P}^{1}\times\mathbb{P}^{1}

factors in part because p(x)p(x) has (for instance) the repeated factors (x21)8\bigl(x^{2}-1\bigr)^{8} in the big piece x3(x21)8x^{3}\,\bigl(x^{2}-1\bigr)^{8}. One sees that {p(x)=p(y)}\{\,p(x)=p(y)\,\} contains (at least) the divisor $${x=y\}$$ plus further factors coming from the roots x=0  or  x=±1,x = 0 \;\text{or}\; x = \pm 1, ensuring multiple irreducible components (and not all of them are hyperplanes).


2. Computing p(19)p(19)

A direct substitution x=19x=19 gives a large integer. Symbolic expansion or a computer algebra system yields

p(19)  =  1934999285524070399999639.p(19) \;=\; 1934999285524070399999639.

Hence the required value is

\boxed{\,p(19) \;=\; 1934999285524070399999639\,}. \] ​:contentReference[oaicite:0]{index=0}​

„OpenAI o3“ teisingai gauna atsakymą nenaudodamas paieškos, o „o1“ nepateikia teisingo atsakymo.

Ekonomiško samprotavimo tobulinimas

Kaina ir našumas: „o3‑mini“ ir „o4-mini“
„OpenAI o3-mini“ ir „o4-mini“ AIME vertinimai
„OpenAI o3-mini“ ir „o4-mini“ GPQA vertinimai
Kaina ir našumas: „o1“ ir „o3“
„OpenAI o3“ ir „o4“ AIME vertinimai
„OpenAI o3“ ir „o4“ GPQA vertinimai

„OpenAI o3“ ir „o4-mini“ yra patys išmaniausi mūsų kada nors išleisti modeliai, be to, jie dažnai yra efektyvesni už savo pirmtakus – „OpenAI o1“ ir „o3‑mini“. Pavyzdžiui, 2025 m. AIME matematikos konkurse „o3“ kainos ir našumo santykis yra akivaizdžiai geresnis nei „o1“, o „o4-mini“ – atitinkamai geresnis nei „o3‑mini“. Apskritai tikimės, kad daugeliu realaus pasaulio naudojimo atvejų „o3“ ir „o4-mini“ bus ir protingesni, ir pigesni nei atitinkamai „o1“ ir „o3‑mini“.

Safety

Each improvement in model capabilities warrants commensurate improvements to safety. For OpenAI o3 and o4-mini, we completely rebuilt our safety training data, adding new refusal prompts in areas such as biological threats (biorisk), malware generation, and jailbreaks. This refreshed data has led o3 and o4-mini to achieve strong performance on our internal refusal benchmarks (e.g., instruction hierarchy, jailbreaks). In addition to strong performance for model refusals, we have also developed system-level mitigations to flag dangerous prompts in frontier risk areas. Similar to our earlier work in image generation, we trained a reasoning LLM monitor which works from human-written and interpretable safety specifications. When applied to biorisk, this monitor successfully flagged ~99% of conversations in our human red‑teaming campaign.

We stress tested both models with our most rigorous safety program to date. In accordance with our updated Preparedness Framework, we evaluated o3 and o4-mini across the three tracked capability areas covered by the Framework: biological and chemical, cybersecurity, and AI self-improvement. Based on the results of these evaluations, we have determined that both o3 and o4‑mini remain below the Framework's "High" threshold in all three categories. We have published the detailed results from these evaluations in the accompanying system card⁠.

„Codex CLI“: pažangiausias samprotavimas terminale

Taip pat dalijamės nauju eksperimentu: „Codex CLI“ – lengvu programavimo agentu, kurį galite paleisti iš savo terminalo. Jis veikia tiesiogiai jūsų kompiuteryje ir sukurtas maksimaliai išnaudoti tokių modelių kaip „o3“ ir „o4-mini“ samprotavimo galimybes; ateityje numatomas papildomų API modelių, tokių kaip GPT‑4.1, palaikymas.

Galite pasinaudoti multimodaliniu samprotavimu komandų eilutėje perduodami ekrano kopijas arba mažo tikslumo eskizus modeliui kartu su prieiga prie kodo vietoje. Laikome tai minimalia sąsaja, skirta sujungti mūsų modelius su naudotojais ir jų kompiuteriais. „Codex CLI“ yra visiškai atvirojo kodo, pasiekiama adresu github.com/openai/codex(atsidaro naujame lange) jau šiandien.

Kartu pradedame 1 mln. JAV dolerių vertės iniciatyvą, skirtą projektams, naudojantiems „Codex CLI“ ir „OpenAI“ modelius, remti. Vertinsime ir priimsime paraiškas dotacijoms po 25 tūkst. JAV dolerių API kreditais. Pasiūlymus galima teikti čia.

Prieiga

„ChatGPT Plus“, „Pro“ ir „Team“ naudotojai nuo šiandien modelio parinkiklyje matys „o3“, „o4-mini“ ir „o4-mini-high“, kurie pakeis „o1“, „o3‑mini“ ir „o3‑mini‑high“. „ChatGPT Enterprise“ ir „Edu“ naudotojai prieigą gaus po savaitės. Plano „Free“ naudotojai gali išbandyti „o4-mini“, prieš pateikdami užklausą žinučių rengyklėje pasirinkę „Think“. Visų planų dažnio limitai išlieka tokie patys kaip ir ankstesnių modelių atveju.

Tikimės per kelias savaites išleisti „OpenAI o3‑pro“ su visu įrankių palaikymu. Kol kas „Pro“ naudotojai vis dar gali naudotis „o1‑pro“.

Tiek „o3“, tiek „o4-mini“ šiandien taip pat prieinami programuotojams per „Chat Completions API“ ir „Responses API“ (kai kuriems programuotojams reikės patvirtinti savo organizacijas(atsidaro naujame lange), kad gautų prieigą prie šių modelių). „Responses API“ palaiko samprotavimo santraukas, galimybę išsaugoti samprotavimo prieigos raktus aplink funkcijų iškvietimus geresniam našumui užtikrinti ir netrukus palaikys integruotus įrankius, tokius kaip paieška internete, failų paieška ir kodo interpretatorius modelio samprotavime. Norėdami pradėti, peržiūrėkite mūsų dokumentaciją(atsidaro naujame lange) ir sekite naujienas.

What's next

Today's updates reflect the direction our models are heading in: we’re converging the specialized reasoning capabilities of the o-series with more of the natural conversational abilities and tool use of the GPT‑series. By unifying these strengths, our future models will support seamless, natural conversations alongside proactive tool use and advanced problem-solving.


Update on July 28, 2025: SWE-Lancer dataset and results updated as of July 17, 2025, available at: https://github.com/openai/preparedness(atsidaro naujame lange) and in our system cards. This update resolves several issues that were impacting the dollars earned results and removes the requirement for internet connectivity during execution, eliminating a primary source of variability in model performance.

Update on April 16, 2025: results for o3 on Charxiv-r and Mathvista were updated to reflect a system prompt change that wasn't present in the original evaluation.

Tiesioginės transliacijos pakartojimas

Autorius

OpenAI

Pastabos

* „Tau-bench“ vertinimo skaičiai yra penkių vykdymo ciklų vidurkis, skirti sumažinti svyravimus ir gauti nenaudojant jokių pasirinktinių įrankių ar raginimų. Nustatėme, kad „tau-bench“ mažmeninės prekybos diegimuose dažniau pasitaiko naudotojo modelio klaidų. Tamsesnių stulpelių skaičiai gauti naudojant GPT-4.1 kaip naudotojo modelį, nes jis gerokai geriau nei „GPT-4o“ laikosi instrukcijų.

* „SWE-bench“ naudoja 256 tūkst. maksimalų konteksto ilgį, o tai pagerina „o4-mini“ sprendimų rodiklį apie 3 proc. ir turi <1 proc. įtaką „o3“ sprendimų rodikliui. Taip pat neįtraukėme 23 pavyzdžių, kurių negalima paleisti mūsų vidinėje infrastruktūroje.

** Įjungus naršymą, modelis kartais gali rasti tikslius atsakymus internete, pavyzdžiui, skaitydamas tinklaraščių įrašus, kuriuose pateikiami pavyzdiniai duomenų rinkinio uždaviniai. Susirūpinimą dėl modelio sukčiavimo naršant mažiname pasitelkę dvi strategijas.

  • Užblokavome domenus, kuriais naudodamasis modelis anksčiau sukčiavo.

  • Naudojame samprotavimo modelį kaip stebėsenos priemonę visiems prieigos raktams kiekvieno bandymo metu tikrinti, siekdami nustatyti įtartiną veikseną. Įtartina veiksena apibrėžiama kaip „puslapis, failas arba fragmentas, kurio pagrindinė paskirtis – pateikti tikslų atsakymą į konkretų klausimą (pvz., oficialus vertinimo raktas, nutekinta „sprendimų“ santrauka arba diskusija, kurioje pažodžiui cituojamas galutinis atsakymas)“. Nekenksminga veiksena apibrėžiama kaip „bet koks patikimas šaltinis, kuriuo galėtų remtis kruopštus žmogus (dokumentacija, vadovai, moksliniai straipsniai, patikimos publikacijos), net jei jame atsitiktinai pateiktas teisingas atsakymas“. Visi bandymai, kuriuos stebėsenos priemonė įvertino kaip įtartinus, laikomi neteisingais. Dauguma pavyzdžių, neatitinkančių šio kriterijaus, buvo uždaviniai, kurių tikslus sprendimas buvo prieinamas keliuose su HLE nesusijusiuose interneto šaltiniuose.

Galiausiai, mūsų vertinimai naudojant naršymą gali būti nevisiškai atkuriami „OpenAI API“ dėl paieškos variklių posistemių skirtumų tarp „ChatGPT“ ir „OpenAI API“. Šie rezultatai skirti atspindėti „ChatGPT“ naudotojų patirtį, tačiau, priklausomai nuo paklausos, paieškos konfigūracija laikui bėgant gali keistis.

Autoriai

Aaditya Singh, Aaron Schlesinger, Adam Fry, Adam Lerer, Adam Perelman, Adam Walker, Ahmed El-Kishky, Aidan Clark, Aidan McLaughlin, Aiden Low, Akila Welihinda, Akshay Nathan, Aleksander Madry, Aleksandra Spyra, Alex Karpenko, Alex Neitz, Alex Tachard Passos, Alex Wei, Alexander Prokofiev, Alexander Zielenski, Alexandra Barr, Alexey Ivanov, Alexi Christakis, Alfred Xue, Allison Tam, Ally Bennett, Ally Bennett , Amelia Liu, Amy McDonald Sandjideh, Ananya Kumar, Andre Saraiva, Andrea Vallone, Andrew Chen, Andrew Duberstein, Andrew Gibiansky, Andrew Kondrich, Andrew Tulloch, Andrey Mishchenko, Andy Applebaum, Andy Wang, Angela Baek, Annie Wei, Anting Shen, Antoine Pelisse, Anuj Saharan, Arun Vijayvergiya, Ashley Tyra, Ashvin Nair, Avi Nayak, Avital Oliver, Behrooz Ghorbani, Belinda Truong, Ben Sokolowsky, Beth Hoover, Bo Xu, Boaz Barak, Bohan Zhang, Borys Minaiev, Botao Hao, Bowen Baker, Bowen Cheng, Brandon McKinzie, Brandon Wang, Brian Hsu, Brian Yang, Brian Yu, Brian Zhang, Camillo Lugaresi, Carolina Paz, Carpus Chang, Cary Bassin , Cary Hudson, Casey Chu, Chak Li, Charles Zhao, Charlie Jatt, Charlotte Cole, Chelsea Voss, Chen Shen, Chengxu Zhuang, Chris Colby, Chris Hallacy , Chris Koch, Christina Kaplan, Christina Kim, Colin Reid, Colin Wei, Cristina Scheau, D. Sculley, Damien Deville, Dan Roberts, Dana Palmie, Dane Stuckey, Daniel Levine, David Hu, David Martin, David Robinson, David Sasaki, Davis Wu, Derek Chen, Dibya Bhattacharjee, Dimitris Tsipras, Dinghua Li, DJ Strouse, dmed Medina, Drew Hintz, Eddie Zhang, Edmund Wong, Elaine Ya Le, Eli Yani , Elizabeth Proehl, Emily Sokolova, Enoch Cheung, Eri Schwartz, Eric Mitchell, Eric Ning, Eric Sigler, Eric Wallace, Eugenio Panero, Evan Mays, Evgenii Nikishin, Fan Wang, Fangyuan Li, Filippo Raso, Foivos Tsimpourlas, Fouad Matin, Francis Song, Francis Zhang, Gary Yang, Gene Oden, Giambattista Parascandolo, Gildas Chabot, Grace Kim, Grace Zhao, Greg Brockman, Gregory Valiant, Guillaume Leclerc, Hadi Salman, Haitang Hu, Hannah Sheahan, Hao Sheng, Haoyu Wang, Henrique Ponde de Oliveira Pinto, Henry Aspegren, Heqing Yan, Hessam Bagherinezhad, Hongyu Ren, Hunter Lightman, Hyeonwoo Noh, Ian Kivlichan, Ian Sohl, Ignasi Clavera, Ikai Lan, Ilge Akkaya, Ilya Kostrikov, Irina Kofman, Isa Fulford, Jake Brill, Jakub Pachocki, James Betker, James Lee, James Qin, Jamie Kiros, Jason Ai, Jay Wang, Jean Harb, Jeff Mickey, Jeffrey Han, Jeffrey Wang, Jeremy Chen, Jerry Tworek, Jessica Liang, Jessica Shieh, Ji Lin, Jiahui Yu, Jianfeng Wang, Jie Tang, Jihan Yin, Jing Li, Joanne Jang, Joel Morris, Johannes Ferstad, Johannes Heidecke, John Fishbein, Jon Okun, Jonathan Gordon, Joost Huizinga, Jos Kraaijeveld, Joseph Mo, Josh Lawson , Josh Tobin, Junhua Mao, Kai Chen, Kai Hayashi, Karan Singhal, Karina Nguyen, Katy Shi, Kelly Stirman, Kenji Hata, Kenny Nguyen, Keren Gu-Lemberg, Kevin Gladstone, Kevin King, Kevin Liu, Kevin Lu, Kevin Park, Kevin Stone, Kevin Weil, Kevin Whinnery, Kevin Yu, Kote Mushegiani, Kristen Ying, Kristian Georgiev, Kshitij Gupta, Kyle Kosic, Lama Ahmad, Larry Lv, Lauren Itow, Lauren Yang, Lee Byron, Leo Chen, Leo Liu, Leon Maksin, Leyton Ho, Li Jing, Liang Xiong, Lin Yang, Linden Li, Lorenz Kuhn, Louis Feuvrier, Lu Zhang, Łukasz Kaiser, Mahmoud Eariby, Maja Trębacz, Manas Joglekar, Manoli Liodakis, Manuka Stratta, Mark Chen, Mark Hudnall, Mark Sun, Mark Wang, Martin Li, Marvin Zhang, Mateusz Litwin, Matt Jones, Matt Lim, Max Johnson, Max Schwarzer, Mayank Gupta, Meghan Shah, Mengqing Wang, Mengyuan Yan, Mia Glaese, Michael Bolin, Michael Lampe, Michael Malek, Michael Sharman, Michael Zhang, Michele Wang, Michelle Pokrass, Miguel Oom Temudo de Castro, Mihai Florian, Mike McClay, Mike Trpcic, Miki Habryn, Miles Wang, Ming Chen, Mingxuan Wang, Minnia Feng, Mitchell Gordon, Mo Bavarian, Mostafa Rohaninejad, Nacho Soto, Nakul Khanna, Nat McAleese, Natalie Staudacher, Natan LaFontaine, Neel Ajjarapu, Nick Felt, Nick Turley, Nikil Pancha, Nikita Mikhaylin, Niko Felix, Nikunj Handa, Ning Liu, Nishant Rai, Noah Jorgensen, Noam Brown, Oleg Boiko, Oleg Murk, Olivia Watkins, Olivier Godement, Oona Gleeson, Paul Ashbourne, Pavel Belov, Peter Flockhart, Peter Hoeschele, Peter Zhokhov, Philip Pronin, Phillip Guo, Phoebe Thacker, Prafulla Dhariwal, Prashanth R, Rachel Dias, Rahul Arora, Rajkumar Samuel, Rasmus Rygaard, Ravi Teja Mullapudi, Raymond Li, Raz Gaon, Reah Miyara, Reiichiro Nakano, Reimar Leike, Rennie Song, Rhythm Garg, RJ Marsan, Robert Xiong, Robin Brown, Roman Tsiupa, Rui Shu, Ruslan Nigmatullin, Saachi Jain, Saagar Patel, Sam Altman, Sam Toizer, Sam Toyer, Samir Ahmed, Samuel Miserendino, Samuel Wolrich , Sandhini Agarwal, Santiago Hernández, Sarah Dong, Savannah Heon, Scott Ethersmith, Scott Mayer McKinney, Sean Fitzgerald, Sever Banesiu, Shamez Hemani, Shengjia Zhao, Shengli Hu, Shibani Santurkar, Shreyas Krishnaswamy, Shuchao Bi, Shunyu Yao, Shuyuan Zhang, Simón Posada Fishman, Spencer Papay, Spug Golden, Srinivas Narayanan, Stanley Hsieh, Stephen Logsdon, Sundeep Tirumalareddy, Tal Stramer, Tao Wang, Tao Xin, Taylor Gordon, Tejal Patwardhan, Thibault Sottiaux, Tina Sriskandarajah, Tony Casparro, Tony Zhao, Trevor Creech, Uzair Navid Iftikhar, Valerie Qi, Vineet Kosaraju, Vishal Kuo, Vitchyr Pong, Vivek Verma, Vlad Petrov, Wenda Zhou, Wenlei Xie, Wenting Zhan, Will DePue, Will Ellsworth, William Sheu, Wyatt Thompson, Yaming Lin, Yann Dubois, Yaodong Yu, Yara Khakbaz, Yash Patil, Yifan Wu, Yilong Qin, Yining Chen, Yirui Zhang, Yo Shavit , Young Cha, Yunyun Wang, Yushi Wang, Zack Sultan, Zehao Dou, Zewei Chu, Zheng Shao, Zhigang Wang, Zhishuai Zhang, Zihao Zhang